Neural networks that process the parameters of other neural networks find applications in domains as diverse as classifying implicit neural representations, generating neural network weights, and predicting generalization errors. However, existing approaches either overlook the inherent permutation symmetry in the neural network or rely on intricate weight-sharing patterns to achieve equivariance, while ignoring the impact of the network architecture itself. In this work, we propose to represent neural networks as computational graphs of parameters, which allows us to harness powerful graph neural networks and transformers that preserve permutation symmetry. Consequently, our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations, predicting generalization performance, and learning to optimize, while consistently outperforming state-of-the-art methods. The source code is open-sourced at https://github.com/mkofinas/neural-graphs.

翻译：处理其他神经网络参数的神经网络在多个领域均有应用，例如隐式神经表示分类、神经网络权重生成以及泛化误差预测。然而，现有方法要么忽视了神经网络固有的置换对称性，要么依赖复杂的权重共享模式来实现等变性，同时忽略了网络架构本身的影响。在本工作中，我们提出将神经网络表示为参数的计算图，从而能够利用保持置换对称性的强大图神经网络和Transformer模型。因此，我们的方法使得单一模型能够编码具有多样化架构的神经计算图。我们在多种任务上展示了本方法的有效性，包括隐式神经表示的分类与编辑、泛化性能预测以及优化学习，其性能始终优于现有最先进方法。源代码已开源：https://github.com/mkofinas/neural-graphs。